Lin Jiaxi, Zhu Shiqi, Gao Xin, Liu Xiaolin, Xu Chunfang, Xu Zhonghua, Zhu Jinzhou
Department of Gastroenterology, The First Affiliated Hospital of Soochow University, Suzhou, China.
Suzhou Clinical Center of Digestive Diseases, Suzhou, China.
Heliyon. 2024 Oct 3;10(19):e38920. doi: 10.1016/j.heliyon.2024.e38920. eCollection 2024 Oct 15.
This study aims to evaluate the value of super resolution (SR) technology in augmenting the quality of digestive endoscopic images.
In the retrospective study, we employed two advanced SR models, , SwimIR and ESRGAN. Two discrete datasets were utilized, with training conducted using the dataset of the First Affiliated Hospital of Soochow University (12,212 high-resolution images) and evaluation conducted using the HyperKvasir dataset (2,566 low-resolution images). Furthermore, an assessment of the impact of enhanced low-resolution images was conducted using a 5-point Likert scale from the perspectives of endoscopists. Finally, two endoscopic image classification tasks were employed to evaluate the effect of SR technology on computer vision (CV).
SwinIR demonstrated superior performance, which achieved a PSNR of 32.60, an SSIM of 0.90, and a VIF of 0.47 in test set. 90 % of endoscopists supported that SR preprocessing moderately ameliorated the readability of endoscopic images. For CV, enhanced images bolstered the performance of convolutional neural networks, whether in the classification task of Barrett's esophagus (improved F1-score: 0.04) or Mayo Endoscopy Score (improved F1-score: 0.04).
SR technology demonstrates the capacity to produce high-resolution endoscopic images. The approach enhanced clinical readability and CV models' performance of low-resolution endoscopic images.
本研究旨在评估超分辨率（SR）技术在提高消化内镜图像质量方面的价值。
在这项回顾性研究中，我们采用了两种先进的SR模型，即SwinIR和ESRGAN。使用了两个独立的数据集，其中使用苏州大学附属第一医院的数据集（12212张高分辨率图像）进行训练，并使用HyperKvasir数据集（2566张低分辨率图像）进行评估。此外，从内镜医师的角度，使用5点李克特量表对增强后的低分辨率图像的影响进行了评估。最后，采用两项内镜图像分类任务来评估SR技术对计算机视觉（CV）的效果。
SwinIR表现出卓越的性能，在测试集中达到了32.60的峰值信噪比（PSNR）、0.90的结构相似性指数（SSIM）和0.47的视觉信息保真度（VIF）。90%的内镜医师支持SR预处理适度改善了内镜图像的可读性。对于CV，增强后的图像提升了卷积神经网络在巴雷特食管分类任务（F1分数提高：0.04）或梅奥内镜评分（F1分数提高：0.04）中的性能。
SR技术证明了生成高分辨率内镜图像的能力。该方法提高了低分辨率内镜图像的临床可读性和CV模型的性能。
